{"url":"/dataset/wikipedia-title","name":"Wikipedia Title","full_name":null,"description_markdown":"**Wikipedia Title** is a dataset for learning character-level compositionality from the character visual characteristics. It consists of a collection of Wikipedia titles in Chinese, Japanese or Korean labelled with the category to which the article belongs.\n\nSource: [https://arxiv.org/abs/1704.04859](https://arxiv.org/abs/1704.04859)","description_withheld":null,"homepage":"https://github.com/frederick0329/Wikipedia_title_dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-character-level-compositionality","title":"Learning Character-level Compositionality with Visual Features","first_author":"Frederick Liu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"},{"name":"Morphological Analysis","url":"/task/morphological-analysis","datasets_with_task":"/datasets/task/morphological-analysis"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Korean","url":"/datasets/language/korean"}],"variants":["Wikipedia Title"],"data_loaders":[{"repo":"https://github.com/frederick0329/Wikipedia_title_dataset","url":"https://github.com/frederick0329/Wikipedia_title_dataset","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}